Eric Hambro

large language model (2) text generation (2) adversarial learning (1) adversarial robustness (1) imitation learning (1) sequential decision making (1) self-supervised learning (1) factual accuracy (1) prompt engineering (1) language modeling (1) model safety (1) early stopping (1) adversarial attack (1) prompt generation (1) tool use (1) adversarial prompt (1) open-ended search (1) quality-diversity optimization (1) attack transferability (1) safety fine-tuning (1)